{"id":"W4384925646","doi":"10.1038/s41467-023-39985-2","title":"Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector","year":2023,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Congressionally Directed Medical Research Programs; National Cancer Institute; National Human Genome Research Institute; Canadian Cancer Society Research Institute; Ovarian Cancer Research Fund; National Institutes of Health; Cancer Research UK; Cycle for Survival; Canadian Institutes of Health Research; Mark Foundation For Cancer Research; Memorial Sloan-Kettering Cancer Center; Marie-Josée and Henry R. Kravis Center for Molecular Oncology; U.S. Department of Defense; Breast Cancer Research Foundation; Stand Up To Cancer","keywords":"Dimensionality reduction; Computer science; Computational biology; Curse of dimensionality; Mutual information; Embedding; Scalability; Gene; Leverage (statistics); Identification (biology); Principal component analysis; Feature vector; Artificial intelligence; Biology; Genetics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007907415,0.0006871969,0.0006714346,0.001157974,0.0002834812,0.001159762,0.0006297982,0.0004766919,0.001391679],"category_scores_gemma":[0.001891233,0.0003359397,0.0008705818,0.001299552,0.0006484499,0.001113537,0.0008362326,0.0009589151,0.0004904371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009868405,"about_ca_system_score_gemma":0.0008663859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00347137,"about_ca_topic_score_gemma":0.005477895,"domain_scores_codex":[0.9995428,0.0001047439,0.00002595759,0.0001691726,0.0001148427,0.00004243889],"domain_scores_gemma":[0.9994149,0.0002387302,0.0000989188,0.0001015035,0.0001110906,0.00003495418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007646889,0.0003132501,0.01122219,0.0006121217,0.0003241825,0.0001911705,0.0006672372,0.38961,0.1421305,0.06125598,0.008683502,0.3842252],"study_design_scores_gemma":[0.00001626581,0.00006123223,0.00197824,0.00001114775,0.00001457639,0.00003151839,0.00004615602,0.9642099,0.01042267,0.02075568,0.002426147,0.00002641927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07153043,0.0002433831,0.9228061,0.000150209,0.00002853544,0.00008715164,0.002002161,0.002471689,0.0006803264],"genre_scores_gemma":[0.5144519,0.0003687932,0.4746746,0.0001448769,0.00003636006,0.0005357368,0.007100471,0.0006641245,0.002023076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00347137,"threshold_uncertainty_score":0.007160068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02417645493662699,"score_gpt":0.2824276157368955,"score_spread":0.2582511608002684,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}